annotate fasta_remove_id.py @ 0:d5c3354c166d draft default tip

Uploaded
author cpt_testbed
date Fri, 29 Apr 2022 10:33:36 +0000
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
1 #!/usr/bin/env python
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
2 import sys
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
3 import argparse
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
4 import logging
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
5 from Bio import SeqIO
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
6
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
7 logging.basicConfig(level=logging.INFO)
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
8 log = logging.getLogger()
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
9
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
10
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
11 def drop_id(fasta_file=None):
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
12 for rec in SeqIO.parse(fasta_file, "fasta"):
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
13 rec.description = ""
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
14 ind = str(rec.seq).find("##")
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
15 if (
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
16 ind != -1
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
17 ): # This method causes mid-file comments (such as from Apollo sequences) to be appended to the end of the previous sequence
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
18 rec.seq = rec.seq[0:ind]
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
19 yield rec
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
20
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
21
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
22 if __name__ == "__main__":
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
23 parser = argparse.ArgumentParser(description="Identify shine-dalgarno sequences")
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
24 parser.add_argument("fasta_file", type=argparse.FileType("r"), help="Genbank file")
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
25
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
26 args = parser.parse_args()
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
27 for rec in drop_id(**vars(args)):
d5c3354c166d Uploaded
cpt_testbed
parents:
diff changeset
28 SeqIO.write([rec], sys.stdout, "fasta")